Model reference · open weights
gemma-3 is an open-weight language model from google, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
Specifications
| Maker | |
|---|---|
| Type | Language models |
| Parameters (lead) | 1000M |
| Variants | 5 |
| Runs with | transformers |
| Based on | google/gemma-3-1b-pt |
| Released | 2025-03-10 |
| Popularity | 3.5M downloads / month |
| Likes | 2,015 |
| Licence | Open, with conditions |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
Using it via the API
Once AxForge deploys gemma-3 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (gemma-3 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gemma-3","messages":[{"role":"user","content":"Hello"}]}'
Details
Tags
Papers
Licence
Open weights under gemma, which carries conditions (e.g. attribution or an acceptable-use clause). Worth a read before production use — we can walk you through it. Read the licence ↗